Adaptive Margin-based Contrastive Network for Generalized Zero-Shot Learning

Jeong Cheol Lee, Athul Shibu, Dong Gyu Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Generalized zero-shot learning is a challenging problem that aims to recognize images from seen and unseen classes. Recent methods are costly and time-consuming or have a bias problem. To tackle this problem, we proposed an adaptive margin-based contrastive network that aims to distinguish similar classes in generalized zero-shot learning. The proposed method employs the architecture of transferable contrastive network to classify unseen classes and adaptive margin to transfer discriminative knowledge. Experiments on the AwA2 dataset demonstrate competitive results against state-of-the-art benchmarks.

Original languageEnglish
Title of host publication2023 IEEE International Conference on Consumer Electronics, ICCE 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665491303
DOIs
StatePublished - 2023
Event2023 IEEE International Conference on Consumer Electronics, ICCE 2023 - Las Vegas, United States
Duration: 6 Jan 20238 Jan 2023

Publication series

NameDigest of Technical Papers - IEEE International Conference on Consumer Electronics
Volume2023-January
ISSN (Print)0747-668X

Conference

Conference2023 IEEE International Conference on Consumer Electronics, ICCE 2023
Country/TerritoryUnited States
CityLas Vegas
Period6/01/238/01/23

Keywords

  • Adaptive margin
  • contrastive network
  • deep learning
  • generalized zero-shot learning
  • zero-shot learning

Cite this